AI safety researcher

Xinpeng Zhang

Shanghai University

Google Scholar dblp ORCID

Last 12 months2 papers

AI safety papers from the last year

On this site: 27 papers

May 2026

Only Train Once: Uncertainty-Aware One-Class Learning for Face Authenticity Detection
May 11arXiv ↗

November 2025

SimuFreeMark: A Noise-Simulation-Free Robust Watermarking Against Image Editing
Nov 14arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.